[youtube] Fix extraction.

[youtube-dl] / youtube_dl / extractor / funimation.py

diff --git a/youtube_dl/extractor/funimation.py b/youtube_dl/extractor/funimation.py
index e44a2a87fa9759b170ed5cc780511a6b42faf695..8bbedca269233b2ba4bdd02febf7d8e63007feb4 100644 (file)
--- a/youtube_dl/extractor/funimation.py
+++ b/youtube_dl/extractor/funimation.py
@@ -1,16 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import random
+import string
+
 from .common import InfoExtractor
-from ..compat import (
-    compat_HTTPError,
-    compat_urllib_parse_unquote_plus,
-)
+from ..compat import compat_HTTPError
 from ..utils import (
     determine_ext,
     int_or_none,
     js_to_json,
-    sanitized_Request,
     ExtractorError,
     urlencode_postdata
 )
@@ -20,6 +19,7 @@ class FunimationIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)'
 
     _NETRC_MACHINE = 'funimation'
+    _TOKEN = None
 
     _TESTS = [{
         'url': 'https://www.funimation.com/shows/hacksign/role-play/',
@@ -38,56 +38,38 @@ class FunimationIE(InfoExtractor):
     }, {
         'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
         'info_dict': {
-            'id': '9635',
+            'id': '210051',
             'display_id': 'broadcast-dub-preview',
             'ext': 'mp4',
             'title': 'Attack on Titan: Junior High - Broadcast Dub Preview',
-            'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803',
             'thumbnail': r're:https?://.*\.(?:jpg|png)',
         },
-        'skip': 'Access without user interaction is forbidden by CloudFlare',
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
         'only_matching': True,
     }]
 
-    _LOGIN_URL = 'http://www.funimation.com/login'
-
-    def _extract_cloudflare_session_ua(self, url):
-        ci_session_cookie = self._get_cookies(url).get('ci_session')
-        if ci_session_cookie:
-            ci_session = compat_urllib_parse_unquote_plus(ci_session_cookie.value)
-            # ci_session is a string serialized by PHP function serialize()
-            # This case is simple enough to use regular expressions only
-            return self._search_regex(
-                r'"user_agent";s:\d+:"([^"]+)"', ci_session, 'user agent',
-                default=None)
-
     def _login(self):
-        (username, password) = self._get_login_info()
+        username, password = self._get_login_info()
         if username is None:
             return
-        data = urlencode_postdata({
-            'email_field': username,
-            'password_field': password,
-        })
-        user_agent = self._extract_cloudflare_session_ua(self._LOGIN_URL)
-        if not user_agent:
-            user_agent = 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'
-        login_request = sanitized_Request(self._LOGIN_URL, data, headers={
-            'User-Agent': user_agent,
-            'Content-Type': 'application/x-www-form-urlencoded'
-        })
-        login_page = self._download_webpage(
-            login_request, None, 'Logging in as %s' % username)
-        if any(p in login_page for p in ('funimation.com/logout', '>Log Out<')):
-            return
-        error = self._html_search_regex(
-            r'(?s)<div[^>]+id=["\']errorMessages["\'][^>]*>(.+?)</div>',
-            login_page, 'error messages', default=None)
-        if error:
-            raise ExtractorError('Unable to login: %s' % error, expected=True)
-        raise ExtractorError('Unable to log in')
+        try:
+            data = self._download_json(
+                'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
+                None, 'Logging in', data=urlencode_postdata({
+                    'username': username,
+                    'password': password,
+                }))
+            self._TOKEN = data['token']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                error = self._parse_json(e.cause.read().decode(), None)['error']
+                raise ExtractorError(error, expected=True)
+            raise
 
     def _real_initialize(self):
         self._login()
@@ -108,7 +90,7 @@ class FunimationIE(InfoExtractor):
 
         video_id = title_data.get('id') or self._search_regex([
             r"KANE_customdimensions.videoID\s*=\s*'(\d+)';",
-            r'<iframe[^>]+src="/player/(\d+)"',
+            r'<iframe[^>]+src="/player/(\d+)',
         ], webpage, 'video_id', default=None)
         if not video_id:
             player_url = self._html_search_meta([
@@ -125,9 +107,14 @@ class FunimationIE(InfoExtractor):
         description = self._html_search_meta(['description', 'og:description'], webpage, fatal=True)
 
         try:
+            headers = {}
+            if self._TOKEN:
+                headers['Authorization'] = 'Token %s' % self._TOKEN
             sources = self._download_json(
-                'https://prod-api-funimationnow.dadcdigital.com/api/source/catalog/video/%s/signed/' % video_id,
-                video_id)['items']
+                'https://www.funimation.com/api/showexperience/%s/' % video_id,
+                video_id, headers=headers, query={
+                    'pinst_id': ''.join([random.choice(string.digits + string.ascii_letters) for _ in range(8)]),
+                })['items']
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
                 error = self._parse_json(e.cause.read(), video_id)['errors'][0]